© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    letes
    -0.84
    76561
    -0.72
     calves
    -0.72
    achine
    -0.71
     gland
    -0.67
    metry
    -0.66
    yip
    -0.66
     Carbuncle
    -0.65
    aminer
    -0.64
     Alger
    -0.63
    POSITIVE LOGITS
     TIME
    0.75
    IGN
    0.70
     DRAG
    0.69
     WOR
    0.68
    hol
    0.68
    CLOSE
    0.67
    ayed
    0.66
    ãĤ½
    0.66
    DCS
    0.66
    TIME
    0.65
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.